{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:53:57Z","timestamp":1790996037050,"version":"4.1.0"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T00:00:00Z","timestamp":1670457600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T00:00:00Z","timestamp":1670457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s11263-022-01722-5","type":"journal-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T18:02:56Z","timestamp":1670522576000},"page":"644-658","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis"],"prefix":"10.1007","volume":"131","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2077-1246","authenticated-orcid":false,"given":"Hao","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip H. S.","family":"Torr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,8]]},"reference":[{"key":"1722_CR1","doi-asserted-by":"crossref","unstructured":"AlBahar, B., & Huang, J.-B. (2019). Guided image-to-image translation with bi-directional feature transformation. In ICCV.","DOI":"10.1109\/ICCV.2019.00911"},{"key":"1722_CR2","unstructured":"Amos, B., Ludwiczuk, B., & Satyanarayanan, M. (2016). Openface: A general-purpose face recognition library with mobile applications. Technical report, CMU-CS-16-118, CMU School of Computer Science."},{"key":"1722_CR3","doi-asserted-by":"crossref","unstructured":"Balakrishnan, G., Zhao, A., Dalca, A. V., Durand, F., & Guttag J. (2018). In CVPR: Synthesizing images of humans in unseen poses.","DOI":"10.1109\/CVPR.2018.00870"},{"key":"1722_CR4","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis. In ICLR"},{"key":"1722_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017). Realtime multi-person 2D pose estimation using part affinity fields. In CVPR","DOI":"10.1109\/CVPR.2017.143"},{"key":"1722_CR6","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., & Efros, A.\u00a0A. (2019). Everybody dance now. In ICCV.","DOI":"10.1109\/ICCV.2019.00603"},{"key":"1722_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Bin, Y., Gao, C., Sang, N., & Tang, H. (2020). Relevant region prediction for crowd counting. Elsevier Neurocomputing.","DOI":"10.1016\/j.neucom.2020.04.117"},{"key":"1722_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Rohrbach, M., Yan, Z., Shuicheng, Y., Yan, S., Feng, J., & Kalantidis, Y. (2019). Graph-based global reasoning networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00052"},{"key":"1722_CR9","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018). Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In CVPR.","DOI":"10.1109\/CVPR.2018.00916"},{"key":"1722_CR10","doi-asserted-by":"crossref","unstructured":"Di, X., Sindagi, V.\u00a0A., & Patel, V.\u00a0M. (2018). GP-GAN: Gender preserving GAN for synthesizing faces from landmarks. In ICPR.","DOI":"10.1109\/ICPR.2018.8545081"},{"key":"1722_CR11","doi-asserted-by":"crossref","unstructured":"Esser, P., Sutter, E., & Ommer, B. A. (2018). variational u-net for conditional appearance and shape generation. In CVPR.","DOI":"10.1109\/CVPR.2018.00923"},{"key":"1722_CR12","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Bing, X., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In NeurIPS."},{"key":"1722_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1722_CR14","doi-asserted-by":"crossref","unstructured":"Huang, S., Xiong, H., Cheng, Z.-Q., Wang, Q., Zhou, X., Wen, B., Huan, J., & Dou, D. (2020). Generating person images with appearance-aware pose stylizer. In IJCAI.","DOI":"10.24963\/ijcai.2020\/87"},{"key":"1722_CR15","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A.\u00a0A. (2017). Image-to-image translation with conditional adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2017.632"},{"key":"1722_CR16","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"1722_CR17","unstructured":"Kim, J., Kim, M., Kang, H., & Lee, K. (2020). U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. In ICLR."},{"key":"1722_CR18","unstructured":"Kingma, D.\u00a0P., & Ba, J. (2015). Adam: A method for stochastic optimization. In ICLR."},{"key":"1722_CR19","unstructured":"Kipf, T.\u00a0N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In ICLR."},{"key":"1722_CR20","doi-asserted-by":"crossref","unstructured":"Langner, O., Dotsch, R., Bijlstra, G., Wigboldus, D.\u00a0H. J., Hawk, S.\u00a0T., & Knippenberg, A. D.\u00a0V. (2010). Presentation and validation of the radboud faces database. Taylor & Francis Cognition and emotion.","DOI":"10.1037\/t76956-000"},{"key":"1722_CR21","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z., & Wu, X.-M. (2018). Deeper insights into graph convolutional networks for semi-supervised learning. In AAAI.","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"1722_CR22","doi-asserted-by":"crossref","unstructured":"Liang, D., Wang, R., Tian, X. & Zou, C. (2019). Pcgan: Partition-controlled human image generation. In AAAI.","DOI":"10.1609\/aaai.v33i01.33018698"},{"key":"1722_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Qiu, S., Wang, X., & Tang, X. (2016). Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In CVPR.","DOI":"10.1109\/CVPR.2016.124"},{"key":"1722_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Piao, Z., Min, J., Luo, W., Ma, L., & Gao, S. (2019). Liquid warping GAN: A unified framework for human motion imitation, appearance transfer and novel view synthesis. In ICCV.","DOI":"10.1109\/ICCV.2019.00600"},{"key":"1722_CR25","doi-asserted-by":"crossref","unstructured":"Liu, G., Tang, H., Latapie, H., & Yan, Y. (2020). Exocentric to egocentric image generation via parallel generative adversarial network. In ICASSP.","DOI":"10.1109\/ICASSP40776.2020.9053957"},{"key":"1722_CR26","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., & Van Luc, G. (2017). Pose guided person image generation. In NeurIPS.","DOI":"10.1109\/CVPR.2018.00018"},{"key":"1722_CR27","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q. Georgoulis, S., Van Gool, L., Schiele, B., & Fritz, M. (2018). Disentangled person image generation. In CVPR.","DOI":"10.1109\/CVPR.2018.00018"},{"key":"1722_CR28","unstructured":"Mejjati, Y. A., Richardt, C., Tompkin, J., Cosker, D., & Kim, K. I. (2018). In NeurIPS: Unsupervised attention-guided image-to-image translation."},{"key":"1722_CR29","unstructured":"Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784."},{"key":"1722_CR30","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.-Y., Wang, T.-C., & Zhu, J.-Y. (2019). Semantic image synthesis with spatially-adaptive normalization. In CVPR.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"1722_CR31","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L, et\u00a0al. (2019). Pytorch: An imperative style, high-performance deep learning library. In NeurIPS."},{"key":"1722_CR32","doi-asserted-by":"crossref","unstructured":"Peng, W., Shi, J., Xia, Z., & Zhao, G. (2020). Mix dimension in poincar\u00e9 geometry for 3d skeleton-based action recognition. In ACM MM.","DOI":"10.1145\/3394171.3413910"},{"key":"1722_CR33","unstructured":"Po-Wei, W., Lin, Y.-J.,Chang, C.-H. Chang, E. Y., & Liao, S.-W. (2019). Relgan: Multi-domain image-to-image translation via relative attributes. In ICCV."},{"issue":"3","key":"1722_CR34","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1007\/s11263-019-01210-3","volume":"128","author":"A Pumarola","year":"2020","unstructured":"Pumarola, A., Agudo, A., Martinez, A. M., Sanfeliu, A., & Moreno-Noguer, F. (2020). Ganimation: One-shot anatomically consistent facial animation. Springer IJCV, 128(3), 698\u2013713.","journal-title":"Springer IJCV"},{"key":"1722_CR35","unstructured":"Ren, B., Tang, H., & Sebe, N. (2021). Cascaded cross mlp-mixer gans for cross-view image translation. In BMVC."},{"key":"1722_CR36","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved techniques for training gans. In NeurIPS."},{"key":"1722_CR37","doi-asserted-by":"crossref","unstructured":"Shaham, T. R., Dekel, T., & Michaeli, T. (2019). Singan: Learning a generative model from a single natural image. In ICCV).","DOI":"10.1109\/ICCV.2019.00467"},{"key":"1722_CR38","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Sangineto, E., Lathuili\u00e8re, S., & Sebe, N. (2018). Deformable gans for pose-based human image generation. In CVPR.","DOI":"10.1109\/CVPR.2018.00359"},{"key":"1722_CR39","unstructured":"Songsong, W., Tang, H., Jing, X.-Y. Zhao, H. Qian, J., Sebe, N., & Yan, Y. (2022). Cross-view panorama image synthesis. IEEE TMM."},{"key":"1722_CR40","doi-asserted-by":"crossref","unstructured":"Tang, H., & Sebe, N. (2021). Layout-to-image translation with double pooling generative adversarial networks. IEEE TIP.","DOI":"10.1109\/TIP.2021.3109531"},{"key":"1722_CR41","doi-asserted-by":"crossref","unstructured":"Tang, H., & Sebe, N. (2021). Total generate: Cycle in cycle generative adversarial networks for generating human faces, hands, bodies, and natural scenes. IEEE TMM.","DOI":"10.1109\/TMM.2021.3091847"},{"key":"1722_CR42","doi-asserted-by":"crossref","unstructured":"Tang, H., Bai, S., & Sebe, N. (2020). Dual attention gans for semantic image synthesis. In ACM MM.","DOI":"10.1145\/3394171.3416270"},{"key":"1722_CR43","doi-asserted-by":"crossref","unstructured":"Tang, H., Bai, S., Zhang, L., Torr, P. H. S., & Sebe, N. (2020). In ECCV: Xinggan for person image generation.","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"1722_CR44","doi-asserted-by":"crossref","unstructured":"Tang, H., Bai, S. Torr, P. H. S., & Sebe, N. (2020). In BMVC: Bipartite graph reasoning gans for person image generation.","DOI":"10.1007\/978-3-030-58595-2_43"},{"key":"1722_CR45","doi-asserted-by":"crossref","unstructured":"Tang, H., Chen, X., Wang, W., Dan, X. Corso, J. J., Sebe, N. & Yan, Y. (2019). In FG: Attribute-guided sketch generation.","DOI":"10.1109\/FG.2019.8756586"},{"key":"1722_CR46","doi-asserted-by":"crossref","unstructured":"Tang, H., Liu, H., & Sebe, N. (2020). Unified generative adversarial networks for controllable image-to-image translation. IEEE TIP.","DOI":"10.1109\/IJCNN.2019.8851881"},{"key":"1722_CR47","doi-asserted-by":"crossref","unstructured":"Tang, H., Liu, H., Dan, X., Torr, P. H. S., & Sebe, N. (2021). Attentiongan: Unpaired image-to-image translation using attention-guided generative adversarial networks. IEEE TNNLS.","DOI":"10.1109\/TNNLS.2021.3105725"},{"key":"1722_CR48","doi-asserted-by":"crossref","unstructured":"Tang, H., Shao, L., Torr, P. H. S. & Sebe, N. (2022). IEEE TPAMI: Local and global gans with semantic-aware upsampling for image generation.","DOI":"10.1109\/TPAMI.2022.3155989"},{"key":"1722_CR49","doi-asserted-by":"crossref","unstructured":"Tang, H., Wang, W., Wu, S., Chen, X., Xu, D., Sebe, N., & Yan, Y. (2019). Expression conditional gan for facial expression-to-expression translation. In ICIP.","DOI":"10.1109\/ICIP.2019.8803654"},{"key":"1722_CR50","doi-asserted-by":"crossref","unstructured":"Tang, H., Wang, W., Xu, D., Yan, Y., & Sebe, N. (2018). Gesturegan for hand gesture-to-gesture translation in the wild. In ACM MM.","DOI":"10.1145\/3240508.3240704"},{"key":"1722_CR51","doi-asserted-by":"crossref","unstructured":"Tang, H., Xu, D., Liu, G., Wang, W., Sebe, N., & Yan, Y. (2019). Cycle in cycle generative adversarial networks for keypoint-guided image generation. In ACM MM.","DOI":"10.1145\/3343031.3350980"},{"key":"1722_CR52","doi-asserted-by":"crossref","unstructured":"Tang, H., Xu, D., Sebe, N., Wang, Y., Corso, J.\u00a0J., & Yan,Y. (2019). Multi-channel attention selection gan with cascaded semantic guidance for cross-view image translation. In CVPR.","DOI":"10.1109\/CVPR.2019.00252"},{"key":"1722_CR53","doi-asserted-by":"crossref","unstructured":"Tang, H., Xu, D., Yan, Y., Torr, P.\u00a0H.S., & Sebe, N. (2020). Local class-specific and global image-level generative adversarial networks for semantic-guided scene generation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00789"},{"key":"1722_CR54","doi-asserted-by":"crossref","unstructured":"Tang, H, Xu, D., Sebe, N., & Yan, Y. (2019). Attention-guided generative adversarial networks for unsupervised image-to-image translation. In IJCNN.","DOI":"10.1109\/IJCNN.2019.8851881"},{"key":"1722_CR55","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Fei, W., Jing, X.-Y., Bao, B.-K., & Xu, C. (2022). Df-gan: A simple and effective baseline for text-to-image synthesis. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"1722_CR56","doi-asserted-by":"crossref","unstructured":"Wang, X., & Gupta, A. (2018). Videos as space-time region graphs. In ECCV.","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"1722_CR57","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, L., Li, Y., & Wang, S. (2019). Linkage based face clustering via graph convolution network. In CVPR.","DOI":"10.1109\/CVPR.2019.00121"},{"issue":"4","key":"1722_CR58","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE TIP, 13(4), 600\u2013612.","journal-title":"IEEE TIP"},{"key":"1722_CR59","doi-asserted-by":"crossref","unstructured":"Wu, S., Tang, H., Jing, X.-Y., Qian, J., Sebe, N., Yan, Y., & Zhang, Q. (2022). Cross-view panorama image synthesis with progressive attention gans. Elsevier PR.","DOI":"10.1016\/j.patcog.2022.108884"},{"key":"1722_CR60","doi-asserted-by":"crossref","unstructured":"Xu, Z., Lin, T., Tang, H., Li, F., He, D., Sebe, N., Timofte, R., Van\u00a0Gool, L., & Ding, E. (2022). Predict, prevent, and evaluate: Disentangled text-driven image manipulation empowered by pre-trained vision-language model. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01769"},{"key":"1722_CR61","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., & Lin, D. (2018). Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1722_CR62","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhan, X., Chen, D., Yan, J., Change Loy, C., & Lin, D. (2019). In CVPR: Learning to cluster faces on an affinity graph.","DOI":"10.1109\/CVPR.2019.00240"},{"key":"1722_CR63","doi-asserted-by":"crossref","unstructured":"Zanfir, M., Popa, A.-I., Zanfir, A., & Sminchisescu, C. (2018). Human appearance transfer. In CVPR.","DOI":"10.1109\/CVPR.2018.00565"},{"key":"1722_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, J., Chen, J., Tang, H., Sangineto, E., Wu, P., Yan, Y., Sebe, N., & Wang, W. (2022). Unsupervised high-resolution portrait gaze correction and animation. IEEE TIP.","DOI":"10.1109\/TIP.2022.3191852"},{"key":"1722_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A., Shechtman, E., & Wang, O. (2018). In CVPR: The unreasonable effectiveness of deep features as a perceptual metric.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1722_CR66","unstructured":"Zhang, L., Li, X., Arnab, A., Yang, K., Tong, Y., & Torr, P.\u00a0H. S. (2019). Dual graph convolutional network for semantic segmentation. In BMVC."},{"key":"1722_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, J., Sangineto, E., Tang, H., Siarohin, A., Zhong, Z., Sebe, N., & Wang, W. (2022). 3D-aware semantic-guided generative model for human synthesis. In ECCV.","DOI":"10.1007\/978-3-031-19784-0_20"},{"key":"1722_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, J., Shu, Y., Xu, S., Cao, G, Zhong, F., Liu, M., & Qin, X. (2018). Sparsely grouped multi-task generative adversarial networks for facial attribute manipulation. In ACM MM.","DOI":"10.1145\/3240508.3240594"},{"key":"1722_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Chen, D., Yuan, L., & Wen, F. (2020). Cross-domain correspondence learning for exemplar-based image translation. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00519"},{"key":"1722_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, L., Liyue Shen, L., Tian, S. W., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In ICCV.","DOI":"10.1109\/ICCV.2015.133"},{"key":"1722_CR71","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., & Bai, X. (2019). Progressive pose attention transfer for person image generation. In CVPR.","DOI":"10.1109\/CVPR.2019.00245"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01722-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01722-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01722-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T07:04:11Z","timestamp":1676617451000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01722-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,8]]},"references-count":71,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["1722"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01722-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,8]]},"assertion":[{"value":"12 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}